© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175391
    Prev
    Next
    INDEX
    Explanations

    latest photos

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_20_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ú
    0.45
    এন
    0.43
     Επι
    0.41
     mill
    0.40
    which
    0.40
     दृश्य
    0.40
    μός
    0.40
     histórica
    0.40
     Mill
    0.39
    ંબ
    0.39
    POSITIVE LOGITS
     steroid
    0.40
    );//
    0.40
     rests
    0.39
     MPA
    0.39
     prí
    0.39
     interfaces
    0.38
    odings
    0.38
     কাটিয়ে
    0.38
                            
    0.38
     Ayurved
    0.38
    Activations Density 0.014%

    No Known Activations